#### PDFs and Images
- PDF documents (text and metadata extraction)
- Images (JPEG, PNG, GIF, TIFF, BMP)
- Image metadata (EXIF, IPTC, XMP)

#### Archives and Compressed Files
- ZIP, TAR, GZ archives
- LHA compression format
- Nested archive extraction

#### Web and Markup
- HTML, XHTML with XPath support
- XML documents
- JSON and structured data

#### Media Files

    private void localDistroSetup() {
        settingsFile << """
        include ":distribution:archives:${testArchiveProjectName}"
        """
        def bwcSubProjectFolder = testProjectDir.newFolder("distribution", "archives", testArchiveProjectName)
        new File(bwcSubProjectFolder, 'current-marker.txt') << "current"
        new File(bwcSubProjectFolder, 'build.gradle') << """

        DEVELOCITY_ACCESS_KEY: ${{ secrets.DEVELOCITY_ACCESS_KEY }}
        # Potential stop-gap solution for ReadTimeout issues with the Gradle Build Cache
        # https://gradle.slack.com/archives/CHDLT99C6/p1636477584059200
        GRADLE_OPTS: -Dhttp.keepAlive=false

    - name: Compile with Gradle without publishing a Build Scan
      if: ${{ matrix.language == 'java' && github.repository_owner != 'gradle' }}

application/hep                hep              # Hummingbird Host Explorer Profiles
application/lotus-123          wks              # Lotus 123
application/mac-binhex40       hqx              # Macintosh binhexed archives
application/mspowerpoint       ppt              # Microsoft Powerpoint
application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File

            projectPath += ":docker:";
            projectPath += distributionProjectName(distribution);
        } else {
            projectPath += distribution.getType() == ElasticsearchDistributionTypes.ARCHIVE ? ":archives:" : ":packages:";
            projectPath += distributionProjectName(distribution);
        }
        return projectPath;
    }

    @Override
    public String getExternalUseErrorMessage() {

./gradlew :distribution:archives:windows-zip:assemble
----

To build distributions for all supported platforms, run:
----
./gradlew assemble
----

Distributions are output to `distributions/archives`.

To run the test suite, see xref:TESTING.asciidoc[TESTING].

[[docs]]
== Documentation

For the complete Elasticsearch documentation visit

        Project distributionProject = ProjectBuilder.builder().withParent(rootProject).withName("distribution").build();
        archivesProject = ProjectBuilder.builder().withParent(distributionProject).withName("archives").build();
        packagesProject = ProjectBuilder.builder().withParent(distributionProject).withName("packages").build();
        bwcProject = ProjectBuilder.builder().withParent(distributionProject).withName("bwc").build();

            }
            tasks.register("buildDarwinZip", Zip) {
                from 'SomeFile.txt'
            }"""
    }

    @Unroll
    def "plain class files in distribution #archiveType archives are detected"() {
        given:
        file("SomeFile.class") << """
            some dummy class file
        """
        buildFile << """
            tasks.withType(AbstractArchiveTask).configureEach {

application/hep                hep              # Hummingbird Host Explorer Profiles
application/lotus-123          wks              # Lotus 123
application/mac-binhex40       hqx              # Macintosh binhexed archives
application/mspowerpoint       ppt              # Microsoft Powerpoint
application/msword             doc              # Microsoft Word
application/octet-stream       bin exe ani      # Binary File

    git clone https://github.com/pyenv/pyenv.git "$PYENV_ROOT"
  fi
  echo "Upgraded pyenv version: $(pyenv --version)"
fi

# Scheduled nightly and release builds upload build artifacts (Pip packages,
# Libtensorflow archives) to GCS buckets. TFCI Mac VMs need to authenticate as
# a service account that has the right permissions to be able to do so.
set +x
if [[ -n "${GOOGLE_APPLICATION_CREDENTIALS:-}" ]]; then